MIST separates scene setup from change execution to isolate memory failures in video world models, and M3-Agent improves ...

🤖 GroundingPI: What foundation model does embodied AI need? 4B parameters. SOTA overall across 34 grounding benchmarks, surpassing GPT-6 Astra! By training precise perception as a native capability, ...

Author here. WebFovea is a vision-based web agent that placed 2nd in the WebRetriever Challenge 2026 (57.0/100). It works on live websites through their own UI: screenshots in, clicks and keystrokes ...

Add files using upload-large-folder tool about 1 year ago meta Add files using upload-large-folder tool about 1 year ago videos Add files using upload-large-folder tool about 1 year ago ...

Remote KV caching for long-context LLM serving can severely degrade latency unless the store is sharded by parallel rank, ...

OneWM unifies causal training of world and action modeling, showing that learning action-conditioned dynamics improves ...

Join the discussion on this paper page Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction ...

Velox accelerates long video rollouts by routing attention via geometric frustum slabs, reducing latency while preserving ...

Timestral is a family of time series foundation models for zero-shot forecasting, available in 5M, 28M, 123M, and 209M parameter versions. This repository contains the 209M checkpoint. Timestral ...

The method converts pre-trained transformers into elastic models that adapt continuously to varying computational budgets by ...

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

This repository contains the weights of the Grok-1 open-weights model. You can find the code in the GitHub Repository. git clone https://github.com/xai-org/grok-1.git ...